Automatic Summarization

@article{Mani2002AutomaticS,
  title={Automatic Summarization},
  author={Inderjeet Mani and Mark T. Maybury},
  journal={Computational Linguistics},
  year={2002},
  volume={28},
  pages={221-223}
}
This paper proposes an automatic speech summarization technique for English. In our proposed method, a set of words maximizing a summarization score indicating appropriateness of summarization is extracted from automatically transcribed speech and concatenated to create a summary. The extraction process is performed using a Dynamic Programming (DP) technique according to a target compression ratio. In this paper, English broadcast news speech transcribed using a speech recognizer is… 
An Empirical Comparison of Contemporary Unsupervised Approaches for Extractive Speech Summarization
TLDR
This study frame automatic summarizaiton task as an ad-hoc information retrieval (IR) problem and employ the mathematical sound language modeling (LM) framework for extractive speech summarization, which can perform important sentence selection in an unsupervised manner and has shown its preliminary success.
Sentence modeling for extractive speech summarization
TLDR
This work explores a novel sentence modeling approach built on top of the notion of relevance, where the relationship between a candidate summary sentence and the spoken document to be summarized is discovered through various granularities of context for relevance modeling.
Effective pseudo-relevance feedback for language modeling in extractive speech summarization
TLDR
This paper explores several effective sentence modeling formulations to enhance the sentence models involved in the LM-based summarization framework and the utilities of the summarization methods are analyzed and compared extensively, which demonstrates the effectiveness of the methods.
Incorporating proximity information in relevance language modeling for extractive speech summarization
  • Shih-Hung Liu, Hung-Shin Lee, +5 authors W. Hsu
  • Computer Science
    2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)
  • 2015
TLDR
Several effective formulations of proximity-based cues for use in the sentence modeling process involved in the LM-based summarization framework are explored and several well-practiced state-of-the-art methods are analyzed and compared extensively.
A recurrent neural network language modeling framework for extractive speech summarization
TLDR
A novel and effective recurrent neural network language modeling (RNNLM) framework for speech summarization, on top of which the deduced sentence models are able to render not only word usage cues but also long-span structural information of word co-occurrence relationships within spoken documents, getting around the need for the strict bag-of-words assumption.
A margin-based discriminative modeling approach for extractive speech summarization
  • Shih-Hung Liu, Kuan-Yu Chen, +4 authors W. Hsu
  • Computer Science
    Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific
  • 2014
TLDR
A novel margin-based discriminative training (MBDT) algorithm that aims to penalize non-summary sentences in an inverse proportion to their summarization evaluation scores, leading to better discrimination from the desired summary sentences is proposed.
Topic and Stylistic Adaptation for Speech Summarisation
TLDR
This paper investigates LiM topic and stylistic adaptation using combinations of LiMs each trained on different adaptation data and finds that summarisation accuracy of automatically generated summaries was significantly improved by automatic LiM adaptation.
A sentence scoring method for extractive text summarization based on Natural language queries
TLDR
A new methodology is proposed for implementing the stoplist concept and statistical analysis concept based on parts of speech tagging and a sentence scoring mechanism has been developed by combining the above methodologies with semantic analysis.
Positional language modeling for extractive broadcast news speech summarization
TLDR
A positional language modeling framework is proposed using different granularities of position-specific information to better estimate the sentence models involved in summarization and to integrate the positional cues into relevance modeling through a pseudo-relevance feedback procedure.
Enhanced language modeling for extractive speech summarization with sentence relatedness information
TLDR
A novel approach that generates overlapped clusters to extract sentence relatedness information from the document to be summarized is explored, which can be used not only to enhance the estimation of various sentence models but also to allow for the sentencelevel structural relationships for better summarization performance.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Advances in automatic speech summarization
TLDR
Japanese broadcast news speech transcribed using a large vocabulary continuous speech recognition (LVCSR) system is summarized using the proposed method and evaluated in comparison with manual summarization by human subjects.
Improvements in automatic speech summarization and evaluation methods
TLDR
Experimental results show that a con dence score giving a penalty for acoustically as well as linguistically unreliable hypotheses can reduce the meaning alteration of summarizations caused by recognition errors especially when the speech recognition rate is relatively low.
Automatic speech summarization based on word significance and linguistic likelihood
  • Chiori Hori, S. Furui
  • Computer Science
    2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
  • 2000
This paper proposes a new method of automatically summarizing speech by extracting a limited number of relatively important words from its automatic transcription according to a target compression
Automatic generation of concise summaries of spoken dialogues in unrestricted domains
TLDR
A global system evaluation shows that for the two more informal genres, the summarization system using dialogue specific components significantly outperforms a baseline using TFIDF term weighting with maximum marginal relevance ranking (MMR).
SUMMARISATION OF SPOKEN AUDIO THROUGH INFORMATION EXTRACTION
TLDR
The results suggest that information extraction based on statistical information can produce viable summaries of decoded audio, and it is demonstrated how extracted summaries, full-text speech recogniser output and audio files can be usefully linked together through an audio-visual interface.
The automatic construction of large-scale corpora for summarization research
TLDR
The algorithm takes as input an Abstract, Text, and generates the corresponding Extract, i.e., the set of clauses (sentences) in the Text that were used to write the Abstract, and is shown to be close to that of humans.
Sentence Reduction for Automatic Text Summarization
TLDR
A novel sentence reduction system for automatically removing extraneous phrases from sentences that are extracted from a document for summarization purpose using multiple sources of knowledge, including syntactic knowledge, context information, and statistics computed from a corpus which consists of examples written by human professionals.
Information extraction and text summarization using linguistic knowledge acquisition
TLDR
The text processing, language acquisition, and summarization components of SCISOR are described, which have been implemented in a prototype intelligent information retrieval system calledSCISOR (System for Conceptual Information Summarization, Organization and Retrieval), which has a number of advantages over traditional document retrieval methods.
The decomposition of human-written summary sentences
TLDR
This work defines the problem of decomposing human-written summary sentences and proposes a novel Hidden Markov Model solution to the problem and sheds light on the generation of summary text by cutting and pasting.
Statistics-Based Summarization - Step One: Sentence Compression
TLDR
This paper focuses on sentence compression, a simpler version of this larger challenge, and aims to achieve two goals simultaneously: the compressions should be grammatical, and they should retain the most important pieces of information.
...
1
2
3
4
5
...